Instructions to use Adaptive-Machine-Patterns/amp-tadpole-lerobot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use Adaptive-Machine-Patterns/amp-tadpole-lerobot with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download NOTICE from Adaptive-Machine-Patterns/amp-tadpole-lerobot: direct link, hf CLI and curl.
- Browser
- Download file 898 Bytes
-
https://huggingface.co/Adaptive-Machine-Patterns/amp-tadpole-lerobot/resolve/main/NOTICE
- Command line
-
hf download hf://Adaptive-Machine-Patterns/amp-tadpole-lerobot/NOTICE
-
curl -L -o NOTICE https://huggingface.co/Adaptive-Machine-Patterns/amp-tadpole-lerobot/resolve/main/NOTICE
898 Bytes
| AMP Tadpole | |
| Copyright 2026 Adaptive Machine Patterns Ltd | |
| (registered in England & Wales, no. 15618869) | |
| The model weights (weights.safetensors, amp-tadpole.onnx), model.py, | |
| config.json and model.yaml are licensed under the Creative Commons | |
| Attribution-NonCommercial 4.0 International licence ( LICENSE). | |
| Commercial licences are available from Adaptive Machine Patterns Ltd: | |
| amp-machine-patterns.com, | |
| https://adaptive-machine-patterns.com/embodied-ai-workbench | |
| instructions.json lists token ids produced the tokenizer of | |
| SmolVLM2-500M-Video-Instruct (HuggingFaceTB), which is licensed under the | |
| Apache License, Version 2.0 ( LICENSE-APACHE-2.0). The tokenizer itself | |
| is not included. AMP Tadpole is not otherwise derived from SmolVLM2: its | |
| weights were trained from scratch. | |
| SmolVLM: Redefining small and efficient multimodal models. | |
| A. Marafioti et al., 2025. arXiv:2504.05299. | |